{"id":"36e64f41-2466-4718-b798-ebe8658d9073","slug":"hf-model-mradermacher-nas-po-grpo-qwen3-vl-8b-gguf-n0onjf-15","name":"NAS-PO-GRPO-Qwen3-VL-8B-GGUF","description":"Hugging Face model mradermacher/NAS-PO-GRPO-Qwen3-VL-8B-GGUF. Task: reinforcement learning. Library: transformers. 734 downloads. 1 likes.","capabilities":["transformers","gguf","vision-language","reinforcement-learning","rlvr","grpo","nas-po","en","dataset:PAPOGalaxy/PAPO_ViRL39K_train","base_model:ANke121/NAS-PO-GRPO-Qwen3-VL-8B","base_model:quantized:ANke121/NAS-PO-GRPO-Qwen3-VL-8B","license:apache-2.0","endpoints_compatible","conversational"],"protocols":[],"safetyScore":80,"overallRank":42,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:27.754Z"}